Skip to main content
Glama

compare_versions

Read-only

Compares two app versions' reviews, ratings, sentiment, category mention shares with z-scores, and patch notes to reveal what changed between releases.

Instructions

Compare two app versions: reviews, rating, sentiment, the share of reviews mentioning each category (with a z-score; |z| >= 2 is roughly significant) and the patch notes in force for each.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "app": "<app>",
      "version_a": "<version_a>",
      "version_b": "<version_b>"
    },
    "name": "compare_versions"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYesGame slug, e.g. critical-strike.
version_aYesBaseline version, e.g. 15.008.
version_bYesVersion to compare, e.g. 15.052.

Output Schema

NameRequiredDescriptionDefault
aYes
bYes
appYes
categoriesYes
examples_bYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds real interpretive context beyond that, notably the '|z| >= 2 is roughly significant' threshold for judging category differences. It does not say how many reviews feed the comparison or whether the sample is time-bounded, which is the remaining behavioral gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the verb and target first, followed by the returned dimensions; the parenthetical z-score note earns its place. The inline enumeration is dense and the line-wrapped formatting is slightly awkward, but nothing is redundant enough to cut.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be spelled out, and the description still previews the compared dimensions to set expectations. Combined with annotations covering read-only behavior, the definition is nearly complete; only the comparison window/sample size is left unstated for a fairly complex analytical tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter already carries a description plus an example ('critical-strike', '15.008'), so baseline semantics are strong. The description reinforces the A/B role split (baseline vs. compared version) and clarifies that patch notes are resolved per-version, adding meaning beyond the raw field types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Compare two app versions') and enumerates exactly what is compared: reviews, rating, sentiment, per-category mention share with z-score, and patch notes. That enumeration distinguishes it from siblings like sentiment_trend (single-metric trend) and search_reviews (raw retrieval) without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The schema-level labels 'Baseline version' and 'Version to compare' imply the intended use and direction of comparison, so the agent knows how to drive it. However, the description gives no explicit when-to-use/when-not guidance and never contrasts itself with search_reviews, sentiment_trend, or top_issues for cases where a version-to-version comparison isn't what the user wants.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.